Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
- Xiaomeng Xu
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Conference paper
Publications
934 results for Trustworthy AI
PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
- Huzaifa Arif
- Keerthiram Murugesan
- et al.
- 2025
- IEEE SaTML 2025
Conference paperTowards Unbiased Evaluation of Time-series Anomaly Detector
- Debarpan Bhattacharya
- Sumanta Mukherjee
- et al.
- 2025
- ICASSP 2025
Conference paperContextual Value Alignment
- Kush Varshney
- Miao Liu
- et al.
- 2025
- ICASSP 2025
Conference paperVP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
- Chia-Yi Hsu
- Jia-You Chen
- et al.
- 2025
- ICASSP 2025
Conference paperMulti-Armed Bandit with Sparse and Noisy Feedback
- Djallel Bouneffouf
- Raphael Feraud
- et al.
- 2025
- ICASSP 2025
Short paperCompliance at the Speed of Innovation: Leveraging AI-Driven Automation for Real-Time Regulatory Read
- Larry Carvalho
- Anca Sailer
- et al.
- 2025
- KubeCon EU 2025
TalkA new framework for evaluating machine learning in biochemistry and its application for small molecules and peptides
- 2025
- IRB-AI-DD 2025
PosterServing LLMs as detectors in workflows with guardrails
- Gaurav Kumbhat
- Evaline Ju
- 2025
- ICSA 2025
Workshop paperCombinatorial Test Design Model Creation using Large Language Models
- Debbie Furman
- Eitan Farchi
- et al.
- 2025
- ICST 2025
Workshop paper